© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 30254
    Prev
    Next
    INDEX
    Explanations

    cache, hardware, architectural terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Overland
    0.45
    NetStandard
    0.40
    disk
    0.40
    蠕
    0.40
    ลิ
    0.40
    磁盘
    0.40
    ält
    0.39
    ře
    0.38
    ズ
    0.38
     disk
    0.37
    POSITIVE LOGITS
    Architect
    0.60
     hardware
    0.57
    硬件
    0.54
    Hardware
    0.54
     tag
    0.52
     tags
    0.52
    Physical
    0.52
     architectural
    0.51
    architect
    0.51
     Architectural
    0.50
    Activations Density 0.007%

    No Known Activations